Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5153 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2473. Min Range: -3.2473

Max Act: 3.2473. Min Act: -0.0001

Data Index: 56405 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.9761. Min Act: -0.0000

Data Index: 154693 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.5817. Min Act: -0.0001

Data Index: 986150 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.5421. Min Act: -0.0001

Data Index: 369371 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.4218. Min Act: -0.0001

Data Index: 838690 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.4263. Min Act: -0.0001

Data Index: 915959 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.3088. Min Act: -0.0001

Data Index: 825303 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.2886. Min Act: -0.0001

Data Index: 49901 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.4022. Min Act: -0.0001

Data Index: 684979 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.3981. Min Act: -0.0001

Data Index: 248662 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.3524. Min Act: -0.0001

Data Index: 1116795 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.5027. Min Act: -0.0001

Data Index: 34626 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.4013. Min Act: -0.0001

Data Index: 896840 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.4007. Min Act: -0.0001

Data Index: 1002581 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.2563. Min Act: -0.0001

Data Index: 900005 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.2372. Min Act: -0.0001

Data Index: 524566 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.0889. Min Act: -0.0000

Data Index: 496866 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.1006. Min Act: -0.0001

Data Index: 1158470 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.0964. Min Act: -0.0001

Data Index: 212178 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 3.2473. Min Range: -3.2473

Max Act: 2.0764. Min Act: -0.0001

Data Index: 36670 (C4 (Web Text))

Max Activating Token Index: 705